Training in progress, step 1200, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 156926880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d28c490785058699a1e8618cc1052385a14f1c2c1441e89fecafc2205d72d9ca
|
| 3 |
size 156926880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 314002891
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed23a7b705bd44c54abea95056794b8b513b6c64cbb9ecd27c2015441d4792a2
|
| 3 |
size 314002891
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c195c9fb096cf067be0bf1bfeb335315e6b38d45cb599558e0bfc1c9b068455c
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a717c54c61f00318563a2243900cad87ed16f178d7acf7675538ea64c8f7c0e3
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -904,6 +904,307 @@
|
|
| 904 |
"learning_rate": 4.1891103844721636e-05,
|
| 905 |
"loss": 1.8271,
|
| 906 |
"step": 896
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 907 |
}
|
| 908 |
],
|
| 909 |
"logging_steps": 7,
|
|
@@ -923,7 +1224,7 @@
|
|
| 923 |
"attributes": {}
|
| 924 |
}
|
| 925 |
},
|
| 926 |
-
"total_flos":
|
| 927 |
"train_batch_size": 8,
|
| 928 |
"trial_name": null,
|
| 929 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.03570844058264272,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 904 |
"learning_rate": 4.1891103844721636e-05,
|
| 905 |
"loss": 1.8271,
|
| 906 |
"step": 896
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.02687060153843865,
|
| 910 |
+
"grad_norm": 2.7906270027160645,
|
| 911 |
+
"learning_rate": 4.108851081114169e-05,
|
| 912 |
+
"loss": 1.7191,
|
| 913 |
+
"step": 903
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.027078900775170733,
|
| 917 |
+
"grad_norm": 1.597091794013977,
|
| 918 |
+
"learning_rate": 4.028828243900141e-05,
|
| 919 |
+
"loss": 1.7157,
|
| 920 |
+
"step": 910
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.027287200011902813,
|
| 924 |
+
"grad_norm": 1.7898212671279907,
|
| 925 |
+
"learning_rate": 3.949063106870031e-05,
|
| 926 |
+
"loss": 1.6832,
|
| 927 |
+
"step": 917
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.027495499248634897,
|
| 931 |
+
"grad_norm": 4.160453796386719,
|
| 932 |
+
"learning_rate": 3.869576835683109e-05,
|
| 933 |
+
"loss": 1.8242,
|
| 934 |
+
"step": 924
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.027703798485366977,
|
| 938 |
+
"grad_norm": 2.273709535598755,
|
| 939 |
+
"learning_rate": 3.790390522001662e-05,
|
| 940 |
+
"loss": 1.6938,
|
| 941 |
+
"step": 931
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.02791209772209906,
|
| 945 |
+
"grad_norm": 1.60932195186615,
|
| 946 |
+
"learning_rate": 3.711525177894331e-05,
|
| 947 |
+
"loss": 1.6732,
|
| 948 |
+
"step": 938
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.028120396958831145,
|
| 952 |
+
"grad_norm": 2.062462091445923,
|
| 953 |
+
"learning_rate": 3.6330017302605576e-05,
|
| 954 |
+
"loss": 1.5316,
|
| 955 |
+
"step": 945
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.028328696195563226,
|
| 959 |
+
"grad_norm": 1.7259407043457031,
|
| 960 |
+
"learning_rate": 3.554841015277641e-05,
|
| 961 |
+
"loss": 1.5854,
|
| 962 |
+
"step": 952
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.02853699543229531,
|
| 966 |
+
"grad_norm": 1.953240156173706,
|
| 967 |
+
"learning_rate": 3.477063772871861e-05,
|
| 968 |
+
"loss": 1.4713,
|
| 969 |
+
"step": 959
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.02874529466902739,
|
| 973 |
+
"grad_norm": 3.1948041915893555,
|
| 974 |
+
"learning_rate": 3.399690641215142e-05,
|
| 975 |
+
"loss": 1.6005,
|
| 976 |
+
"step": 966
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.028953593905759474,
|
| 980 |
+
"grad_norm": 2.461402177810669,
|
| 981 |
+
"learning_rate": 3.322742151248725e-05,
|
| 982 |
+
"loss": 1.9629,
|
| 983 |
+
"step": 973
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.029161893142491558,
|
| 987 |
+
"grad_norm": 2.2598836421966553,
|
| 988 |
+
"learning_rate": 3.246238721235283e-05,
|
| 989 |
+
"loss": 1.9584,
|
| 990 |
+
"step": 980
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.02937019237922364,
|
| 994 |
+
"grad_norm": 1.823764681816101,
|
| 995 |
+
"learning_rate": 3.1702006513409396e-05,
|
| 996 |
+
"loss": 1.4632,
|
| 997 |
+
"step": 987
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.029578491615955722,
|
| 1001 |
+
"grad_norm": 1.822013258934021,
|
| 1002 |
+
"learning_rate": 3.09464811824863e-05,
|
| 1003 |
+
"loss": 1.5673,
|
| 1004 |
+
"step": 994
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.029786790852687803,
|
| 1008 |
+
"grad_norm": 1.8545750379562378,
|
| 1009 |
+
"learning_rate": 3.019601169804216e-05,
|
| 1010 |
+
"loss": 1.5401,
|
| 1011 |
+
"step": 1001
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.029995090089419887,
|
| 1015 |
+
"grad_norm": 2.142122983932495,
|
| 1016 |
+
"learning_rate": 2.9450797196968023e-05,
|
| 1017 |
+
"loss": 1.541,
|
| 1018 |
+
"step": 1008
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.03020338932615197,
|
| 1022 |
+
"grad_norm": 2.207737684249878,
|
| 1023 |
+
"learning_rate": 2.8711035421746367e-05,
|
| 1024 |
+
"loss": 1.6909,
|
| 1025 |
+
"step": 1015
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.03041168856288405,
|
| 1029 |
+
"grad_norm": 1.393803596496582,
|
| 1030 |
+
"learning_rate": 2.7976922667980272e-05,
|
| 1031 |
+
"loss": 1.5975,
|
| 1032 |
+
"step": 1022
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.030619987799616135,
|
| 1036 |
+
"grad_norm": 2.638187885284424,
|
| 1037 |
+
"learning_rate": 2.7248653732306316e-05,
|
| 1038 |
+
"loss": 1.6129,
|
| 1039 |
+
"step": 1029
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.030828287036348215,
|
| 1043 |
+
"grad_norm": 1.743645191192627,
|
| 1044 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 1045 |
+
"loss": 1.621,
|
| 1046 |
+
"step": 1036
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.0310365862730803,
|
| 1050 |
+
"grad_norm": 2.1193864345550537,
|
| 1051 |
+
"learning_rate": 2.581041869722519e-05,
|
| 1052 |
+
"loss": 1.3971,
|
| 1053 |
+
"step": 1043
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.031244885509812383,
|
| 1057 |
+
"grad_norm": 2.1348867416381836,
|
| 1058 |
+
"learning_rate": 2.5100834233126823e-05,
|
| 1059 |
+
"loss": 1.5024,
|
| 1060 |
+
"step": 1050
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.03145318474654447,
|
| 1064 |
+
"grad_norm": 1.6680853366851807,
|
| 1065 |
+
"learning_rate": 2.4397856756471432e-05,
|
| 1066 |
+
"loss": 1.3568,
|
| 1067 |
+
"step": 1057
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.03166148398327655,
|
| 1071 |
+
"grad_norm": 2.6139674186706543,
|
| 1072 |
+
"learning_rate": 2.3701672802157566e-05,
|
| 1073 |
+
"loss": 1.5204,
|
| 1074 |
+
"step": 1064
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.03186978322000863,
|
| 1078 |
+
"grad_norm": 2.4763057231903076,
|
| 1079 |
+
"learning_rate": 2.3012467102424373e-05,
|
| 1080 |
+
"loss": 1.5295,
|
| 1081 |
+
"step": 1071
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.032078082456740716,
|
| 1085 |
+
"grad_norm": 1.9144788980484009,
|
| 1086 |
+
"learning_rate": 2.23304225378328e-05,
|
| 1087 |
+
"loss": 1.8166,
|
| 1088 |
+
"step": 1078
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.032286381693472796,
|
| 1092 |
+
"grad_norm": 1.9162483215332031,
|
| 1093 |
+
"learning_rate": 2.1655720088738453e-05,
|
| 1094 |
+
"loss": 1.6142,
|
| 1095 |
+
"step": 1085
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.032494680930204876,
|
| 1099 |
+
"grad_norm": 2.354734182357788,
|
| 1100 |
+
"learning_rate": 2.0988538787268374e-05,
|
| 1101 |
+
"loss": 1.7982,
|
| 1102 |
+
"step": 1092
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.03270298016693696,
|
| 1106 |
+
"grad_norm": 2.0897438526153564,
|
| 1107 |
+
"learning_rate": 2.0329055669814934e-05,
|
| 1108 |
+
"loss": 1.6379,
|
| 1109 |
+
"step": 1099
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.032911279403669044,
|
| 1113 |
+
"grad_norm": 2.5271339416503906,
|
| 1114 |
+
"learning_rate": 1.9677445730059346e-05,
|
| 1115 |
+
"loss": 1.5626,
|
| 1116 |
+
"step": 1106
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.033119578640401125,
|
| 1120 |
+
"grad_norm": 1.9526691436767578,
|
| 1121 |
+
"learning_rate": 1.9033881872537006e-05,
|
| 1122 |
+
"loss": 1.5815,
|
| 1123 |
+
"step": 1113
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.033327877877133205,
|
| 1127 |
+
"grad_norm": 2.1989901065826416,
|
| 1128 |
+
"learning_rate": 1.8398534866757454e-05,
|
| 1129 |
+
"loss": 1.8776,
|
| 1130 |
+
"step": 1120
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.03353617711386529,
|
| 1134 |
+
"grad_norm": 1.9625588655471802,
|
| 1135 |
+
"learning_rate": 1.7771573301890664e-05,
|
| 1136 |
+
"loss": 1.4475,
|
| 1137 |
+
"step": 1127
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.03374447635059737,
|
| 1141 |
+
"grad_norm": 2.7089996337890625,
|
| 1142 |
+
"learning_rate": 1.715316354203188e-05,
|
| 1143 |
+
"loss": 1.7354,
|
| 1144 |
+
"step": 1134
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.03395277558732945,
|
| 1148 |
+
"grad_norm": 2.1591153144836426,
|
| 1149 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 1150 |
+
"loss": 1.6762,
|
| 1151 |
+
"step": 1141
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.03416107482406154,
|
| 1155 |
+
"grad_norm": 2.157672882080078,
|
| 1156 |
+
"learning_rate": 1.594265350408039e-05,
|
| 1157 |
+
"loss": 1.8244,
|
| 1158 |
+
"step": 1148
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.03436937406079362,
|
| 1162 |
+
"grad_norm": 2.2080414295196533,
|
| 1163 |
+
"learning_rate": 1.5350874434525142e-05,
|
| 1164 |
+
"loss": 1.6367,
|
| 1165 |
+
"step": 1155
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.0345776732975257,
|
| 1169 |
+
"grad_norm": 2.246075391769409,
|
| 1170 |
+
"learning_rate": 1.4768289501820265e-05,
|
| 1171 |
+
"loss": 1.6959,
|
| 1172 |
+
"step": 1162
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.03478597253425778,
|
| 1176 |
+
"grad_norm": 1.6588751077651978,
|
| 1177 |
+
"learning_rate": 1.4195053294732758e-05,
|
| 1178 |
+
"loss": 1.5196,
|
| 1179 |
+
"step": 1169
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.03499427177098987,
|
| 1183 |
+
"grad_norm": 1.9793294668197632,
|
| 1184 |
+
"learning_rate": 1.3631317921347563e-05,
|
| 1185 |
+
"loss": 1.6595,
|
| 1186 |
+
"step": 1176
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.03520257100772195,
|
| 1190 |
+
"grad_norm": 1.935530424118042,
|
| 1191 |
+
"learning_rate": 1.3077232968705805e-05,
|
| 1192 |
+
"loss": 1.7511,
|
| 1193 |
+
"step": 1183
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.03541087024445403,
|
| 1197 |
+
"grad_norm": 1.967477560043335,
|
| 1198 |
+
"learning_rate": 1.2532945463111855e-05,
|
| 1199 |
+
"loss": 1.53,
|
| 1200 |
+
"step": 1190
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.03561916948118612,
|
| 1204 |
+
"grad_norm": 3.320049524307251,
|
| 1205 |
+
"learning_rate": 1.1998599831119912e-05,
|
| 1206 |
+
"loss": 1.6357,
|
| 1207 |
+
"step": 1197
|
| 1208 |
}
|
| 1209 |
],
|
| 1210 |
"logging_steps": 7,
|
|
|
|
| 1224 |
"attributes": {}
|
| 1225 |
}
|
| 1226 |
},
|
| 1227 |
+
"total_flos": 2.384195670245376e+17,
|
| 1228 |
"train_batch_size": 8,
|
| 1229 |
"trial_name": null,
|
| 1230 |
"trial_params": null
|